Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    astronomical references

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens (years, reference indices, page numbers, etc.) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ULATE
    -0.06
    Cont
    -0.06
    ACHER
    -0.06
     Supern
    -0.06
    SUB
    -0.06
     pedal
    -0.06
    _TRACK
    -0.06
    erot
    -0.06
    ��
    -0.06
    bec
    -0.06
    POSITIVE LOGITS
    （笑
    0.07
    -en
    0.07
    ("/")↵
    0.07
     tỉnh
    0.07
    願い
    0.07
     '/',
    0.06
    liği
    0.06
     ↵            ↵
    0.06
     حاضر
    0.06
     oğlu
    0.06
    Act Density 0.000%

    No Known Activations